{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VTANFJSTABNAOFWBXTORZRU7CZ","short_pith_number":"pith:VTANFJST","canonical_record":{"source":{"id":"2506.14220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T06:17:19Z","cross_cats_sorted":[],"title_canon_sha256":"346ad37cd0a68cf59d8791e907a38c639389393879e815212c375c135ceb17a6","abstract_canon_sha256":"b111dea94d3cc1a996e80cef127e9dade73d74445df43ab7c31399ba4899d671"},"schema_version":"1.0"},"canonical_sha256":"acc0d2a653005a0716c1bcdd1cc69f164839d94ace21483f78967c6eea8953e4","source":{"kind":"arxiv","id":"2506.14220","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14220","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14220v2","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14220","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"VTANFJSTABNA","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"VTANFJSTABNAOFWB","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"VTANFJST","created_at":"2026-07-05T11:48:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VTANFJSTABNAOFWBXTORZRU7CZ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.14220","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T06:17:19Z","cross_cats_sorted":[],"title_canon_sha256":"346ad37cd0a68cf59d8791e907a38c639389393879e815212c375c135ceb17a6","abstract_canon_sha256":"b111dea94d3cc1a996e80cef127e9dade73d74445df43ab7c31399ba4899d671"},"schema_version":"1.0"},"canonical_sha256":"acc0d2a653005a0716c1bcdd1cc69f164839d94ace21483f78967c6eea8953e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:26.707480Z","signature_b64":"vIQjUWTpUVZGVSDUO2YZYgAyPY9f0vD48M60wtwy4CwINBvOsYoyL1l3jsf65pP4R8zhwcdHqQXuGdkQqEeRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc0d2a653005a0716c1bcdd1cc69f164839d94ace21483f78967c6eea8953e4","last_reissued_at":"2026-07-05T11:48:26.706995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:26.706995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.14220","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+wOAFxh3bi6T5iLVPlFjVN+LZiQGJEc7MzJpLYdBzgQ4ORFxCIElVC9J6a4QXwULU/xXD9efrdzucTxAslVTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T10:10:49.487013Z"},"content_sha256":"78d049911315f9298ddf5c42c11c06373102003d9ee45b951edc6864e089ce40","schema_version":"1.0","event_id":"sha256:78d049911315f9298ddf5c42c11c06373102003d9ee45b951edc6864e089ce40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VTANFJSTABNAOFWBXTORZRU7CZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophily","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kangkang Lu, Tat-Seng Chua, Yanhua Yu, Zhiyong Huang","submitted_at":"2025-06-17T06:17:19Z","abstract_excerpt":"Spectral Graph Neural Networks (SGNNs) have achieved remarkable performance in tasks such as node classification due to their ability to learn flexible filters. Typically, these filters are learned under the supervision of downstream tasks, enabling SGNNs to adapt to diverse structural patterns. However, in scenarios with limited labeled data, SGNNs often struggle to capture the optimal filter shapes, resulting in degraded performance, especially on graphs with heterophily. Meanwhile, the rapid progress of Large Language Models (LLMs) has opened new possibilities for enhancing graph learning w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14220","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.14220/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i2pevCA7gvRdy/W3JP7c0Qg65Upx3FfWt3uFfN2YGeCUre7XYP2GMkVF7JKaNsE8LhWQAzbYSJ1Sfiz5+iKgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T10:10:49.487400Z"},"content_sha256":"985a6054e2e7443ae74a109701d81ccd9656bcff3a01fcd03cb2e9a1f89d6442","schema_version":"1.0","event_id":"sha256:985a6054e2e7443ae74a109701d81ccd9656bcff3a01fcd03cb2e9a1f89d6442"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTANFJSTABNAOFWBXTORZRU7CZ/bundle.json","state_url":"https://pith.science/pith/VTANFJSTABNAOFWBXTORZRU7CZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTANFJSTABNAOFWBXTORZRU7CZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-16T10:10:49Z","links":{"resolver":"https://pith.science/pith/VTANFJSTABNAOFWBXTORZRU7CZ","bundle":"https://pith.science/pith/VTANFJSTABNAOFWBXTORZRU7CZ/bundle.json","state":"https://pith.science/pith/VTANFJSTABNAOFWBXTORZRU7CZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTANFJSTABNAOFWBXTORZRU7CZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VTANFJSTABNAOFWBXTORZRU7CZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b111dea94d3cc1a996e80cef127e9dade73d74445df43ab7c31399ba4899d671","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T06:17:19Z","title_canon_sha256":"346ad37cd0a68cf59d8791e907a38c639389393879e815212c375c135ceb17a6"},"schema_version":"1.0","source":{"id":"2506.14220","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14220","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14220v2","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14220","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"VTANFJSTABNA","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"VTANFJSTABNAOFWB","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"VTANFJST","created_at":"2026-07-05T11:48:26Z"}],"graph_snapshots":[{"event_id":"sha256:985a6054e2e7443ae74a109701d81ccd9656bcff3a01fcd03cb2e9a1f89d6442","target":"graph","created_at":"2026-07-05T11:48:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.14220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spectral Graph Neural Networks (SGNNs) have achieved remarkable performance in tasks such as node classification due to their ability to learn flexible filters. Typically, these filters are learned under the supervision of downstream tasks, enabling SGNNs to adapt to diverse structural patterns. However, in scenarios with limited labeled data, SGNNs often struggle to capture the optimal filter shapes, resulting in degraded performance, especially on graphs with heterophily. Meanwhile, the rapid progress of Large Language Models (LLMs) has opened new possibilities for enhancing graph learning w","authors_text":"Kangkang Lu, Tat-Seng Chua, Yanhua Yu, Zhiyong Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T06:17:19Z","title":"Enhancing Spectral Graph Neural Networks with LLM-Predicted Homophily"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14220","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78d049911315f9298ddf5c42c11c06373102003d9ee45b951edc6864e089ce40","target":"record","created_at":"2026-07-05T11:48:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b111dea94d3cc1a996e80cef127e9dade73d74445df43ab7c31399ba4899d671","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T06:17:19Z","title_canon_sha256":"346ad37cd0a68cf59d8791e907a38c639389393879e815212c375c135ceb17a6"},"schema_version":"1.0","source":{"id":"2506.14220","kind":"arxiv","version":2}},"canonical_sha256":"acc0d2a653005a0716c1bcdd1cc69f164839d94ace21483f78967c6eea8953e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc0d2a653005a0716c1bcdd1cc69f164839d94ace21483f78967c6eea8953e4","first_computed_at":"2026-07-05T11:48:26.706995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:26.706995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vIQjUWTpUVZGVSDUO2YZYgAyPY9f0vD48M60wtwy4CwINBvOsYoyL1l3jsf65pP4R8zhwcdHqQXuGdkQqEeRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:26.707480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14220","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78d049911315f9298ddf5c42c11c06373102003d9ee45b951edc6864e089ce40","sha256:985a6054e2e7443ae74a109701d81ccd9656bcff3a01fcd03cb2e9a1f89d6442"],"state_sha256":"58dafd59f3dee423a5442403e43846d76a40cafc5596479a33374161af207636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIfd+BrCq8xC4z/Mg2Ve8esr8cFD9fjaek9zEgOSl1Rg/3gEzC4mj6kuLPhOdsAEWlDOcYzP3upwDvtIveReAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T10:10:49.489750Z","bundle_sha256":"cac42db74e39587365963b32e77f5c26ef6de4f1c921dbf06e790f0ca5500170"}}